documentation

A specialist agent for technical documentation and documentation quality checks. It covers docstrings, spelling, writing style, links, and configured documentation rules.

In plain words
What is it for?
Use it when writing or reviewing technical documentation, public method docstrings, style-guide compliance, spelling, links, or Vale and codespell checks.
Why use it?
It helps keep documentation complete and consistent, and catches issues that ordinary code checks may not detect.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/ansys/pymapdl/documentation
Clone the repo
git clone --depth 1 https://github.com/ansys/pymapdl
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 814 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00814
Opus 5 $0.00017 $0.00407
Sonnet 5 $0.00007 $0.00163
Haiku 4.5 $0.00003 $0.00081

Measured yesterday against content hash db45f448e3f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/agents/documentation.agent.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Specialist Agent

Docstrings

All public methods need numpydoc-style docstrings with at minimum: Summary, Parameters, Returns, and Examples. Validation rules are in [tool.numpydoc_validation] in pyproject.toml.

Spelling and style

  • Spell checker: codespell (configured in pyproject.toml)
  • Style linter: vale (configured in doc/.vale.ini and doc/styles/)
  • Add new technical terms to doc/styles/config/vocabularies/ANSYS/accept.txt

Quality Checklist

  • Are parameters documented?
  • Are return values documented?
  • Are exceptions documented?
  • Are examples runnable and clear?
  • Is narrative consistent?
  • Does vale pass?
  • Does codespell pass?
  • Are links in links.rst updated?

Recommendations

  • Prefer active voice and direct language in documentation for clarity and engagement.
  • Put the why before the link. For example, instead of saying "See the documentation for :meth:mapdl.run() <ansys.mapdl.core.Mapdl.run> method for more details", say "To execute a command in MAPDL, use :meth:mapdl.run() <ansys.mapdl.core.Mapdl.run> method. For more information, see the documentation for :meth:mapdl.run() <ansys.mapdl.core.Mapdl.run>."
  • As in the Google style guide, use sentence case for titles.
  • Use U.S. spellings instead of U.K. spellings.
  • Prefer non-hyphenated words. For example postprocessing instead of post-processing.
  • Include a noun after a code entity to indicate its type.
  • Make sure the Sphinx roles (:meth:, :class:, :func:, and others) are properly formatted and consistent with numpydoc style and writing.
  • Use simple form of verbs in headings (rather than "-ing" forms).
  • Add links to relevant sections of the PyMAPDL documentation when mentioning specific features or commands, using the appropriate Sphinx directives to ensure proper linking and formatting.
  • Either consistently include or consistently omit concluding punctuation in code comments.

Key conventions

  • Use Ansys, not ANSYS (except copyright notices)
  • U.S. spellings; no hyphens where avoidable (postprocessing, not post-processing)
  • Sentence case for headings
  • Active voice; put the why before the link
  • Avoid Latin abbreviations (e.g., i.e., etc.) — use for example, that is, and so on
  • Avoid location words like above and below
  • Always include the noun after a code entity (e.g., "the run() method")
  • Use the correct Sphinx role (:meth:, :func:, :class:, etc.) with the full dotted path:
    :func:`save_ansys_path() <ansys.mapdl.core.save_ansys_path>`
    

Read the full file on GitHub · 76 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 76 lines · 35 tokens per session scan A db45f448e3f5

Subscribe to this mod's changes

documentation is an agent published in the GitHub repository ansys/pymapdl (513 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 814 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.